suppressPackageStartupMessages({
library(data.table)
library(DESeq2)
library(gplots)
library(here)
library(hyperSpec)
library(parallel)
library(pander)
library(plotly)
library(tidyverse)
library(tximport)
library(vsn)
library(zinbwave)
library(Rtsne)
})
source(here("UPSCb-common/src/R/featureSelection.R"))
hpal <- colorRampPalette(c("blue","white","red"))(100)
samples <- read_csv(here("doc/samples_final.csv"))
## Parsed with column specification:
## cols(
## ScilifeID = col_character(),
## SubmittedID = col_character(),
## Stages = col_character(),
## Description = col_character(),
## ID = col_character()
## )
filelist <- list.files(here("data/Salmon"),
recursive = TRUE,
pattern = "quant.sf",
full.names = TRUE)
Sanity check to ensure that the data is sorted according to the sample info
filelist <- filelist[match(samples$ScilifeID,sub("_sortmerna.*","",basename(dirname(filelist))))]
stopifnot(all(match(sub("_sortmerna.*","",basename(dirname(filelist))),
samples$ScilifeID) == 1:nrow(samples)))
name the file list vector
names(filelist) <- samples$ID
Read the expression at the gene level
counts <- suppressMessages(round(tximport(files = filelist,
type = "salmon",
txOut=TRUE)$counts))
combine technical replicates
samples$ID <- sub("_L00[1,2]", "",
samples$ScilifeID)
counts <- do.call(
cbind,
lapply(split.data.frame(t(counts),
samples$ID),
colSums))
csamples <- samples[,-1]
csamples <- csamples[match(colnames(counts),csamples$ID),]
read the expression for the pool of lincRNAs we found
linc_read <- read_delim("~/Git/lncRNAs/doc/time_expression_nc_filtered.tsv",
delim = " ")
## Parsed with column specification:
## cols(
## Transcript.ID = col_character(),
## score = col_double(),
## S1 = col_double(),
## S2 = col_double(),
## S3 = col_double(),
## S4 = col_double(),
## S5 = col_double(),
## S6 = col_double(),
## S7 = col_double(),
## S8 = col_double(),
## maxn = col_double(),
## n = col_double(),
## peak = col_character()
## )
linc <- linc_read$Transcript.ID
counts <- counts[linc, ]
sel <- rowSums(counts) == 0
sprintf("%s%% percent (%s) of %s genes are not expressed",
round(sum(sel) * 100/ nrow(counts),digits=1),
sum(sel),
nrow(counts))
## [1] "0% percent (0) of 147984 genes are not expressed"
dat <- tibble(x=colnames(counts),y=colSums(counts)) %>%
bind_cols(csamples)
ggplot(dat,aes(x,y,fill=csamples$Stages)) + geom_col() +
scale_y_continuous(name="reads") +
theme(axis.text.x=element_text(angle=90,size=4),axis.title.x=element_blank())
i.e. the mean raw count of every gene across samples is calculated and displayed on a log10 scale.
The cumulative gene coverage is as expected, considering we have lincRNAs, caracterised by a really low signal.
ggplot(data.frame(value=log10(rowMeans(counts))),aes(x=value)) +
geom_density() + ggtitle("gene mean raw counts distribution") +
scale_x_continuous(name="mean raw counts (log10)")
The same is done for the individual samples colored by Stages.
dat <- as.data.frame(log10(counts)) %>% utils::stack() %>%
mutate(Stages=csamples$Stages[match(ind,csamples$ID)])
ggplot(dat,aes(x=values,group=ind,col=Stages)) +
geom_density() + ggtitle("sample raw counts distribution") +
scale_x_continuous(name="per gene raw counts (log10)")
## Warning: Removed 2743771 rows containing non-finite values (stat_density).
dir.create(here("data/analysis/salmon"),showWarnings=FALSE,recursive=TRUE)
write.csv(counts,file=here("data/analysis/salmon/raw-unormalised-gene-expression_data_linc.csv"))
For visualization, the data is submitted to a variance stabilization transformation using DESeq2. The dispersion is estimated independently of the sample tissue and replicate.
csamples$Stages <- factor(csamples$Stages)
there are a lot of zeros, so we use zinbwave
se <- SummarizedExperiment(assays=list(counts=as.matrix(counts)),
colData=as.data.frame(csamples))
zinb <- zinbwave(se,K=0,epsilon=1e12,
X="~Stages",
observationalWeights=TRUE)
save(zinb,file=here("data/analysis/salmon/zinb.rda"))
Check the size factors (i.e. the sequencing library size effect)
dds <- DESeqDataSet(zinb,design=~Stages)
## converting counts to integer mode
dds <- DESeq(dds,
sfType = "poscounts",
useT = TRUE,
minmu = 1e-6)
## estimating size factors
## estimating dispersions
## gene-wise dispersion estimates
## Warning in getAndCheckWeights(object, modelMatrix, weightThreshold = weightThreshold): for 7311 row(s), the weights as supplied won't allow parameter estimation, producing a
## degenerate design matrix. These rows have been flagged in mcols(dds)$weightsFail
## and treated as if the row contained all zeros (mcols(dds)$allZero set to TRUE).
## If you are blocking for donors/organisms, consider design = ~0+donor+condition.
## mean-dispersion relationship
## final dispersion estimates
## fitting model and testing
save(dds,file=here("data/analysis/salmon/dds_linc.rda"))
vsd <- varianceStabilizingTransformation(dds, blind=TRUE)
vst <- assay(vsd)
vst <- vst - min(vst)
save(vst,file=here("data/analysis/DE/vst-blind_linc.rda"))
vsda <- varianceStabilizingTransformation(dds, blind=FALSE)
vsta <- assay(vsda)
vsta <- vsta - min(vsta)
save(vsta,file=here("data/analysis/DE/vst-aware_linc.rda"))
# prepare the data to build the network
#ID <- rownames(vsta)
#vsta <- cbind(ID,vsta)
#vsta_tibble <- as_tibble(vsta)
#write_tsv(vsta_tibble,path=here("data/analysis/DE/vst-aware_linc.tsv"))
meanSdPlot(log2(counts(dds)[!mcols(dds)$allZero,]+1))
meanSdPlot(log2(assay(zinb)+1))
meanSdPlot(vst[rowSums(vst)>0,])
meanSdPlot(vsta[rowSums(vsta)>0,])
pc <- prcomp(t(vsta))
percent <- round(summary(pc)$importance[2,]*100)
We define the number of variable of the model
nvar=1
And the number of possible combinations
nlevel=nlevels(dds$Stages)
We plot the percentage explained by the different components, the red line represent the number of variable in the model, the orange line the number of variable combinations.
ggplot(tibble(x=1:length(percent),y=cumsum(percent)),aes(x=x,y=y)) +
geom_line() + scale_y_continuous("variance explained (%)",limits=c(0,100)) +
scale_x_continuous("Principal component") +
geom_vline(xintercept=nvar,colour="red",linetype="dashed",size=0.5) +
geom_hline(yintercept=cumsum(percent)[nvar],colour="red",linetype="dashed",size=0.5) +
geom_vline(xintercept=nlevel,colour="orange",linetype="dashed",size=0.5) +
geom_hline(yintercept=cumsum(percent)[nlevel],colour="orange",linetype="dashed",size=0.5)
pc.dat <- bind_cols(PC1=pc$x[,1],
PC2=pc$x[,2],
csamples)
p <- ggplot(pc.dat,aes(x=PC1,y=PC2,col=dds$Stages,text=dds$ID)) +
geom_point(size=2) +
ggtitle("Principal Component Analysis",subtitle="variance stabilized counts")
ggplotly(p) %>%
layout(xaxis=list(title=paste("PC1 (",percent[1],"%)",sep="")),
yaxis=list(title=paste("PC2 (",percent[2],"%)",sep="")))
Filter for noise
conds <- factor(csamples$Stages)
sels <- rangeFeatureSelect(counts=vsta,
conditions=conds,
nrep=3)
## Warning in xy.coords(x, y, xlabel, ylabel, log): 1 y value <= 0 omitted from
## logarithmic plot
vst.cutoff <- 1
mar <- par("mar")
par(mar=c(0.05,0.05,0.05,0.05))
hm <- heatmap.2(t(scale(t(vsta[sels[[vst.cutoff+1]],]))),
distfun=pearson.dist,
hclustfun=function(X){hclust(X,method="ward.D2")},
labRow = NA,trace = "none",
labCol = conds,
col=hpal)
plot(as.hclust(hm$colDendrogram),xlab="",sub="",labels=conds)
# The Biological QA is good, considering it's based on lincRNAs. We have no outliers.
# The sequencing depth decreased comparing to the previous analysis.
# Looking at the PCA, it could be interesting to do DE analysis to see in particular what's going on
# in S3 and S6. I consider those two stages relevant, because I think things are changes here.
#
## R version 4.0.0 (2020-04-24)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.4 LTS
##
## Matrix products: default
## BLAS/LAPACK: /usr/lib/x86_64-linux-gnu/libopenblasp-r0.2.20.so
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] grid parallel stats4 stats graphics grDevices utils
## [8] datasets methods base
##
## other attached packages:
## [1] Rtsne_0.15 zinbwave_1.10.0
## [3] SingleCellExperiment_1.10.1 vsn_3.56.0
## [5] tximport_1.16.1 forcats_0.5.0
## [7] stringr_1.4.0 dplyr_1.0.0
## [9] purrr_0.3.4 readr_1.3.1
## [11] tidyr_1.1.0 tibble_3.0.1
## [13] tidyverse_1.3.0 plotly_4.9.2.1
## [15] pander_0.6.3 hyperSpec_0.99-20200527
## [17] xml2_1.3.2 ggplot2_3.3.2
## [19] lattice_0.20-41 here_0.1
## [21] gplots_3.0.3 DESeq2_1.28.1
## [23] SummarizedExperiment_1.18.1 DelayedArray_0.14.0
## [25] matrixStats_0.56.0 Biobase_2.48.0
## [27] GenomicRanges_1.40.0 GenomeInfoDb_1.24.2
## [29] IRanges_2.22.2 S4Vectors_0.26.1
## [31] BiocGenerics_0.34.0 data.table_1.12.8
##
## loaded via a namespace (and not attached):
## [1] colorspace_1.4-1 ellipsis_0.3.1 rprojroot_1.3-2
## [4] XVector_0.28.0 fs_1.4.1 rstudioapi_0.11
## [7] hexbin_1.28.1 farver_2.0.3 affyio_1.58.0
## [10] bit64_0.9-7 AnnotationDbi_1.50.0 fansi_0.4.1
## [13] lubridate_1.7.9 splines_4.0.0 geneplotter_1.66.0
## [16] knitr_1.29 jsonlite_1.7.0 Cairo_1.5-12
## [19] broom_0.5.6 annotate_1.66.0 dbplyr_1.4.4
## [22] png_0.1-7 BiocManager_1.30.10 compiler_4.0.0
## [25] httr_1.4.1 backports_1.1.8 assertthat_0.2.1
## [28] Matrix_1.2-18 lazyeval_0.2.2 limma_3.44.3
## [31] cli_2.0.2 htmltools_0.5.0 tools_4.0.0
## [34] gtable_0.3.0 glue_1.4.1 GenomeInfoDbData_1.2.3
## [37] affy_1.66.0 Rcpp_1.0.4.6 softImpute_1.4
## [40] cellranger_1.1.0 vctrs_0.3.1 preprocessCore_1.50.0
## [43] gdata_2.18.0 nlme_3.1-148 crosstalk_1.1.0.1
## [46] xfun_0.15 testthat_2.3.2 rvest_0.3.5
## [49] lifecycle_0.2.0 gtools_3.8.2 XML_3.99-0.3
## [52] edgeR_3.30.3 zlibbioc_1.34.0 scales_1.1.1
## [55] hms_0.5.3 RColorBrewer_1.1-2 yaml_2.2.1
## [58] memoise_1.1.0 latticeExtra_0.6-29 stringi_1.4.6
## [61] RSQLite_2.2.0 highr_0.8 genefilter_1.70.0
## [64] caTools_1.18.0 BiocParallel_1.22.0 rlang_0.4.6
## [67] pkgconfig_2.0.3 bitops_1.0-6 evaluate_0.14
## [70] labeling_0.3 htmlwidgets_1.5.1 bit_1.1-15.2
## [73] tidyselect_1.1.0 magrittr_1.5 R6_2.4.1
## [76] generics_0.0.2 DBI_1.1.0 pillar_1.4.4
## [79] haven_2.3.1 withr_2.2.0 survival_3.2-3
## [82] RCurl_1.98-1.2 modelr_0.1.8 crayon_1.3.4
## [85] KernSmooth_2.23-17 rmarkdown_2.3 jpeg_0.1-8.1
## [88] locfit_1.5-9.4 readxl_1.3.1 blob_1.2.1
## [91] reprex_0.3.0 digest_0.6.25 xtable_1.8-4
## [94] munsell_0.5.0 viridisLite_0.3.0